English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This paper presents the network load balancing problem, a challengingreal-world task for multi-agent reinforcement learning (MARL) methods.Traditional heuristic solutions like Weighted-Cost Multi-Path (WCMP) and LocalShortest Queue (LSQ) are less flexible to the changing workload distributionsand arrival rates, with a poor balance among multiple load balancers. Thecooperative network load balancing task is formulated as a Dec-POMDP problem,which naturally induces the MARL methods. To bridge the reality gap forapplying learning-based methods, all methods are directly trained and evaluatedon an emulation system from moderate-to large-scale. Experiments on realistictestbeds show that the independent and "selfish" load balancing strategies arenot necessarily the globally optimal ones, while the proposed MARL solution hasa superior performance over different realistic settings. Additionally, thepotential difficulties of MARL methods for network load balancing are analysed,which helps to draw the attention of the learning and network communities tosuch challenges.

Multi-Agent Reinforcement Learning for Network Load Balancing in Data Center